Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27434
    Prev
    Next
    INDEX
    Explanations

    references to ultrasound technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.26
    1.5%
    219
    +0.16
    1.0%
    71
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.26
    0.01
    71
    +0.16
    0.01
    508
    +0.15
    0.01
    Negative Logits
     varying
    -1.56
    woke
    -1.50
     bargaining
    -1.45
    uk
    -1.44
     happier
    -1.40
     unexpected
    -1.39
     sleeping
    -1.38
     married
    -1.37
    eter
    -1.34
    hots
    -1.33
    POSITIVE LOGITS
    thouse
    1.66
    clesiast
    1.55
    istor
    1.53
    iop
    1.52
    -,
    1.49
    dem
    1.46
    probe
    1.41
    borne
    1.41
    olta
    1.38
    path
    1.36
    Activations Density 0.122%

    No Known Activations